render-web-services
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch up-to-date documentation directly from Render's official website (render.com) using tools like curl. This process ensures the agent uses current platform specifications for deployments, health checks, and networking configuration.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions create an attack surface for indirect prompt injection by requiring the agent to ingest and process content from external documentation URLs.
- Ingestion points: Documentation URLs for deployments, health checks, workflows, rollbacks, and deploy hooks located in references/deployments.md, references/persistent-disks.md, and references/private-networking.md.
- Boundary markers: The skill lacks explicit instructions to treat the fetched markdown content as untrusted data or to use delimiters to prevent instruction injection.
- Capability inventory: The skill provides instructions for the agent to use network-fetching tools (curl) and to guide high-privilege operations such as configuring ports, custom domains, and deployment lifecycles.
- Sanitization: No specific sanitization or validation steps are provided for the agent to perform on the fetched external content before it is incorporated into the session context.
Audit Metadata